Extraction of multi-scale features enhances the deep learning-based daily PM2.5 forecasting in cities. (December 2022)

• Record Type: Journal Article
• Authors: Dong, Liang; Hua, Pei; Gui, Dongwei; Zhang, Jin
• Is Part Of: Chemosphere. Volume 308:Part 2(2022)
• Publication Date: 2022-12
• Subjects: Multi-scale features extractions -- Deep learning -- Hybrid modelling -- PM2.5 -- Two-stage decomposition; Pollution -- Periodicals; Pollution -- Physiological effect -- Periodicals; Environmental sciences -- Periodicals; Atmospheric chemistry -- Periodicals; 551.511
• DOI: 10.1016/j.chemosphere.2022.136252
• Languages: English
• ISSNs: 0045-6535

Abstract

Abstract: Characterising the daily PM2.5 concentration is crucial for air quality control. To govern the status of the atmospheric environment, a novel hybrid model for PM2.5 forecasting was proposed by introducing a two-stage decomposition technology of complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and variational mode decomposition (VMD); subsequently, a deep learning approach of long short-term memory (LSTM) was proposed. Five cities with unique meteorological and economic characteristics were selected to assess the predictive ability of the proposed model. The results revealed that PM2.5 pollution was generally more severe in inland cities (66.98 ± 0.76 μg m −3 ) than in coastal cities (40.46 ± 0.40 μg m-3). The modelling comparison showed that in each city, the secondary decomposition algorithm improved the accuracy and prediction stability of the prediction models. When compared with other prediction models, LSTM effectively extracted featured information and achieved relatively accurate time-series prediction. The hybrid model of CEEMDAN-VMD-LSTM achieved a better prediction in the five cities ( R2 = 0.9803 ± 0.01) compared with the benchmark models ( R2 = 0.7537 ± 0.03). The results indicate that the proposed approach can identify the inherent correlations and patterns among complex datasets, particularly in time-series analysis. Graphical abstract: Image 1 Highlights: Multi-scale features of original data set were extracted by dual decomposition. Decomposition could effectively extract the sequence feature information. Secondary decomposition could further improve the model performance. Long short-term memory neural networks outperformed other shallow networks. Deep learning based on dual decomposition made effective predictions of PM2.5